稠密检索论文趋势 2023–2026
双塔与 ANN
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 401 篇被归入该主题的论文。
主要结论
- 稠密检索论文从 2023 年的 60 篇增长到 2026 年的 162 篇，三年间扩大到约 2.7 倍。
- CVPR 是发稠密检索论文最多的会议，2023–2026 年共 147 篇，占四个会议总量的 37%。
- 交叉方向里涨得最快的是检索记忆：同时属于两个主题的论文从 2023 年的 1 篇增至 2026 年的 21 篇。
- 在「信息检索」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的交叉编码重排是 3.0 倍，稠密检索是 2.7 倍。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 6 | 12 | 8 | 34 | 60 |
| 2024 | 23 | 14 | 22 | 33 | 92 |
| 2025 | 35 | 12 | 10 | 30 | 87 |
| 2026 | 51 | 26 | 35 | 50 | 162 |
代表论文
按年份和会议均匀挑选，方便快速看到每一届的样貌
- NeurIPS 2026Half-Truths Break Similarity-Based Retrieval
- ICML 2026Deep Discriminative Structure Proxy Hashing for Cross-modal Retrieval
- ICLR 2026A Dense Subset Index for Collective Query Coverage
- CVPR 2026Beyond Caption-Based Queries in Video Moment Retrieval
- NeurIPS 2025Dense Associative Memory with Epanechnikov Energy
- ICML 2025Nonparametric Modern Hopfield Models
- ICLR 2025Contextual Document Embeddings
- CVPR 2025Adapting Dense Matching for Homography Estimation with Grid-based Acceleration
- NeurIPS 2024CARE: a Benchmark Suite for the Classification and Retrieval of Enzymes
- ICML 2024Compute Better Spent: Replacing Dense Layers with Structured Matrices
- ICLR 2024Adaptive Retrieval and Scalable Indexing for k-NN Search with Cross-Encoders
- CVPR 2024Dense Optical Tracking: Connecting the Dots
- NeurIPS 2023Bypassing spike sorting: Density-based decoding using spike localization from dense multielectrode probes
- ICML 2023Everyone's Preference Changes Differently: A Weighted Multi-Interest Model For Retrieval
- ICLR 2023Automating Nearest Neighbor Search Configuration with Constrained Optimization
- CVPR 2023Are Binary Annotations Sufficient? Video Moment Retrieval via Hierarchical Uncertainty-Based Active Learning
- NeurIPS 2026Hyperparameter Transfer for Dense Associative Memories
- ICML 2026Dense associative memory for Gaussian distributions
- ICLR 2026Beyond Instance-Level Alignment: Dual-Level Optimal Transport for Audio-Text Retrieval
- CVPR 2026Beyond Tie Points Satellite Image Block Adjustment based on Dense
全部稠密检索论文
共 401 篇，第 5 / 9 页
- ICLR 2025ReNovo: Retrieval-Based \emph{De Novo} Mass Spectrometry Peptide Sequencing
- ICLR 2025Retrieval Head Mechanistically Explains Long-Context Factuality
- ICLR 2025The Journey Matters: Average Parameter Count over Pre-training Unifies Sparse and Dense Scaling Laws
- ICLR 2025Youku Dense Caption: A Large-scale Chinese Video Dense Caption Dataset and Benchmarks
- ICML 2025Contradiction Retrieval via Contrastive Learning with Sparsity
- ICML 2025Distributed Nonparametric Estimation: from Sparse to Dense Samples per Terminal
- ICML 2025In-Context Denoising with One-Layer Transformers: Connections between Attention and Associative Memory Retrieval
- ICML 2025In-Context Learning as Conditioned Associative Memory Retrieval
- ICML 2025Learnware Specification via Dual Alignment
- ICML 2025Locality Preserving Markovian Transition for Instance Retrieval
- ICML 2025MUDDFormer: Breaking Residual Bottlenecks in Transformers via Multiway Dynamic Dense Connections
- ICML 2025Nonparametric Modern Hopfield Models
- ICML 2025POQD: Performance-Oriented Query Decomposer for Multi-vector retrieval
- ICML 2025SHE: Streaming-media Hashing Retrieval
- NeurIPS 2025CellCLIP - Learning Perturbation Effects in Cell Painting via Text-Guided Contrastive Learning
- NeurIPS 2025Contextual Tokenization for Graph Inverted Indices
- NeurIPS 2025CPRet: A Dataset, Benchmark, and Model for Retrieval in Competitive Programming
- NeurIPS 2025Dense Associative Memory with Epanechnikov Energy
- NeurIPS 2025Dense Backpropagation Improves Training for Sparse Mixture-of-Experts
- NeurIPS 2025Dense Metric Depth Estimation via Event-based Differential Focus Volume Prompting
- NeurIPS 2025Dense SAE Latents Are Features, Not Bugs
- NeurIPS 2025Domain Adaptive Hashing Retrieval via VLM Assisted Pseudo-Labeling and Dual Space Adaptation
- NeurIPS 2025Dynamic Masking and Auxiliary Hash Learning for Enhanced Cross-Modal Retrieval
- NeurIPS 2025Efficiently Maintaining the Multilingual Capacity of MCLIP in Downstream Cross-Modal Retrieval Tasks
- NeurIPS 2025Empower Words: DualGround for Structured Phrase and Sentence-Level Temporal Grounding
- NeurIPS 2025EUGens: Efficient, Unified and General Dense Layers
- NeurIPS 2025Exploring Structural Degradation in Dense Representations for Self-supervised Learning
- NeurIPS 2025Fixed-Point RNNs: Interpolating from Diagonal to Dense
- NeurIPS 2025FlowFeat: Pixel-Dense Embedding of Motion Profiles
- NeurIPS 2025Generalized Contrastive Learning for Universal Multimodal Retrieval
- NeurIPS 2025Global Minimizers of Sigmoid Contrastive Loss
- NeurIPS 2025Grids Often Outperform Implicit Neural Representation at Compressing Dense Signals
- NeurIPS 2025Hierarchical Retrieval: The Geometry and a Pretrain-Finetune Recipe
- NeurIPS 2025JAFAR: Jack up Any Feature at Any Resolution
- NeurIPS 2025Learning Dense Hand Contact Estimation from Imbalanced Data
- NeurIPS 2025MERIT: Multilingual Semantic Retrieval with Interleaved Multi-Condition Query
- NeurIPS 2025Optimal community detection in dense bipartite graphs
- NeurIPS 2025Optimizing Retrieval for RAG via Reinforced Contrastive Learning
- NeurIPS 2025Reconciling Geospatial Prediction and Retrieval via Sparse Representations
- NeurIPS 2025REN: Fast and Efficient Region Encodings from Patch-Based Image Encoders
- NeurIPS 2025Results of the Big ANN: NeurIPS’23 competition
- NeurIPS 2025Sparse Meets Dense: Unified Generative Recommendations with Cascaded Sparse-Dense Representations
- NeurIPS 2025STRAP: Spatio-Temporal Pattern Retrieval for Out-of-Distribution Generalization
- NeurIPS 2025Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders
- NeurIPS 2025UFM: A Simple Path towards Unified Dense Correspondence with Flow
- NeurIPS 2025Understanding protein function with a multimodal retrieval-augmented foundation model
- NeurIPS 2025VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold
- NeurIPS 2025VoxDet: Rethinking 3D Semantic Scene Completion as Dense Object Detection
- NeurIPS 2025When One Moment Isn't Enough: Multi-Moment Retrieval with Cross-Moment Interactions
- CVPR 2024Attribute-Guided Pedestrian Retrieval: Bridging Person Re-ID with Internal Attribute Variability
在 Claude、Cursor 里直接问这个趋势
接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。
可以直接复制这句话问 AI
用 paperlist 查稠密检索在 CVPR 2023–2026 的论文趋势，哪一年涨得最快？
AI 会调用的工具：get_topic_stats {"topic": "dense-retrieval"}
常见问题
- 2023–2026 年四大会议一共有多少篇稠密检索论文？
- 共 401 篇，按年份分别是 2023 年 60 篇、2024 年 92 篇、2025 年 87 篇、2026 年 162 篇。
- NeurIPS 2026 有多少篇稠密检索论文？
- NeurIPS 2026 有 51 篇稠密检索论文，上一届是 35 篇。
- ICLR 2026 有多少篇稠密检索论文？
- ICLR 2026 有 26 篇稠密检索论文，上一届是 12 篇。
- ICML 2026 有多少篇稠密检索论文？
- ICML 2026 有 35 篇稠密检索论文，上一届是 10 篇。
- CVPR 2026 有多少篇稠密检索论文？
- CVPR 2026 有 50 篇稠密检索论文，上一届是 30 篇。
- 哪个会议的稠密检索论文最多？
- CVPR，2023–2026 年共 147 篇。